Text-Aware Image Restoration with Diffusion Models
This addresses the issue of inaccurate text reconstruction in degraded images for computer vision applications, representing a domain-specific incremental improvement.
The paper tackles the problem of text-image hallucination in diffusion-based image restoration by introducing a new task, Text-Aware Image Restoration (TAIR), and a benchmark SA-Text with 100K annotated images, resulting in a method that outperforms state-of-the-art approaches with significant gains in text recognition accuracy.
Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those methods frequently generate plausible but incorrect text-like patterns, a phenomenon we refer to as text-image hallucination. In this paper, we introduce Text-Aware Image Restoration (TAIR), a novel restoration task that requires the simultaneous recovery of visual contents and textual fidelity. To tackle this task, we present SA-Text, a large-scale benchmark of 100K high-quality scene images densely annotated with diverse and complex text instances. Furthermore, we propose a multi-task diffusion framework, called TeReDiff, that integrates internal features from diffusion models into a text-spotting module, enabling both components to benefit from joint training. This allows for the extraction of rich text representations, which are utilized as prompts in subsequent denoising steps. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art restoration methods, achieving significant gains in text recognition accuracy. See our project page: https://cvlab-kaist.github.io/TAIR/